Coderabbit

CodeRabbit reviews pull requests with AI on GitHub, GitLab, Azure DevOps and Bitbucket, and reviews local changes from a CLI before they are pushed. Use when a user asks to set up automated PR reviews, write or validate a .coderabbit.yaml, add path-specific review instructions, control a review with @coderabbitai commands, or run coderabbit review from the terminal or a coding agent.

213 stars 34 forksSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add TerminalSkills/skills --skill coderabbit
Manual install
git clone --depth 1 https://github.com/TerminalSkills/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/coderabbit ~/.claude/skills/coderabbit

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# CodeRabbit — AI-Powered Code Review

## Overview

CodeRabbit is a hosted AI code review service. Once installed on a repository it reviews every new pull request: a summary and walkthrough at the top, inline comments with suggested fixes, and the findings of the linters and security scanners it runs for you. Behaviour is configured in a `.coderabbit.yaml` at the repository root, steered per pull request with `@coderabbitai` comments, and the same review engine is available locally through the `coderabbit` CLI (the docs' short alias `cr` is created only by the vendor's install script, not by the installs shown below).

## Instructions

### Setup

1. Sign up at https://app.coderabbit.ai with a GitHub, GitLab, Azure DevOps or Bitbucket account.
2. Add the repositories CodeRabbit may access (on GitHub this installs the CodeRabbit app on the selected repositories).
3. Commit a `.coderabbit.yaml` to the repository root. The file on the branch under review is the one used for that review.
4. Open a pull request — the review arrives as comments from `@coderabbitai`.

Plans: reviews of public repositories are free. Private repositories get a 14-day trial; after it the Free plan keeps PR summaries plus IDE and CLI reviews, and full PR reviews need a paid plan (Essentials, Team, Advanced, Enterprise). Prices and per-developer hourly review limits are on https://www.coderabbit.ai/pricing.

### Configuration
Read the full skill on GitHub

Details

Skill name
coderabbit
Path
skills/coderabbit/SKILL.md
License
Apache-2.0
Repo updated
8 November 2026

FAQ

What does the Coderabbit skill do?

CodeRabbit reviews pull requests with AI on GitHub, GitLab, Azure DevOps and Bitbucket, and reviews local changes from a CLI before they are pushed. Use when a user asks to set up automated PR reviews, write or validate a .coderabbit.yaml, add path-specific review instructions, control a review with @coderabbitai commands, or run coderabbit review from the terminal or a coding agent.

How do I install the Coderabbit skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add TerminalSkills/skills --skill coderabbit. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Coderabbit popular?

It lives in TerminalSkills/skills, which has 213 GitHub stars and 34 forks.

Related skills

3dsmax Rendering

213

TerminalSkills/skills

Scripts and configures production rendering in Autodesk 3ds Max with the V-Ray and Corona renderers: output size and files, render elements, denoising, light mix, batch and command-line rendering, and network rendering. Use when a user asks to set up a production render, render several cameras in one batch, render from the command line or on a render farm, add render passes for compositing, or cut render time for archviz and product shots.

Other34

3dsmax Scripting

213

TerminalSkills/skills

Covers scripting Autodesk 3ds Max, the 3D modeling and rendering application, with MAXScript and Python (pymxs): scene manipulation, object creation, material assignment, camera and light setup, batch operations, and file I/O. Use when tasks involve automating repetitive 3ds Max workflows, batch processing scenes, running scripts headless with 3dsmaxbatch, creating custom tools, or scripting scene setup for archviz, product visualization, or VFX.

Productivity & Notes34

3proxy

213

TerminalSkills/skills

3proxy is a small open-source proxy server that runs HTTP/HTTPS, SOCKS4/5, SNI and TCP/UDP port-mapping proxies from one config file. Use when a user asks to set up an HTTP or SOCKS5 proxy, add proxy users and passwords, write 3proxy access rules, chain or rotate upstream (parent) proxies, limit bandwidth, connections or monthly traffic per user, run 3proxy in Docker, or fix a 3proxy.cfg that will not start.

DevOps & Cloud34

Cohere API

213

TerminalSkills/skills

Cohere API for enterprise NLP — embeddings, reranking, RAG, and text generation. Use when building RAG pipelines, semantic search, document reranking, or enterprise NLP applications. The Command A models handle tool use and retrieval-augmented generation with citations; Embed and Rerank models improve search quality.

Software Development34

Codegraph

213

TerminalSkills/skills

CodeGraph indexes a source tree into a local SQLite knowledge graph of symbols, calls and imports, and serves it to coding agents over MCP and a CLI. Use it when an agent burns tool calls on grep and file reads to understand a codebase, or when you need callers, callees, blast radius or affected tests for a symbol. Covers install, `codegraph init`, query/explore/impact/affected commands, MCP registration, exclusions and troubleshooting. Triggers: "index my repo for the agent", "who calls this function", "what breaks if I change this", "codegraph".

Software Development34

Commander

213

TerminalSkills/skills

Build CLI tools with Commander.js. Use when creating command-line applications, parsing arguments, implementing subcommands, or building developer tools with flags and options.

Software Development34

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.